Triple
T8284203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | P (packed-SIMD extension) |
E193751
|
entity |
| Predicate | dataParallelismModel |
P5328
|
FINISHED |
| Object | packed data parallelism |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: packed data parallelism | Statement: [P (packed-SIMD extension), dataParallelismModel, packed data parallelism]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dataParallelismModel Context triple: [P (packed-SIMD extension), dataParallelismModel, packed data parallelism]
-
A.
isParallelizable
Indicates that a process, task, or operation can be decomposed into independent parts that may be executed concurrently without affecting correctness.
-
B.
concurrentModel
Indicates that two or more processes, activities, or states occur or are valid at the same time, potentially interacting or overlapping in execution.
-
C.
performanceModel
Indicates a relationship where one entity serves as a performance model that represents, predicts, or characterizes the performance behavior of another entity.
-
D.
distributedProgram
Indicates that an entity is responsible for handing out, circulating, or otherwise making a program (such as an agenda, schedule, or software package) available to others.
-
E.
executionModel
chosen
Indicates how a process, task, or operation is carried out or implemented, specifying the underlying method, strategy, or mechanism of its execution.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca82e217a48190880695635c44b2ed |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7ad0535081908bb234cfc0e32b32 |
completed | March 31, 2026, 7:42 a.m. |
| PD | Predicate disambiguation | batch_69cb70ad9fc081908741f8c4a4141edf |
completed | March 31, 2026, 6:58 a.m. |
Created at: March 30, 2026, 5:52 p.m.